1 Baikouquan Oil Production Plant, PetroChina Xinjiang Oilfield Company, Karamay 834000, China
2 School of Sciences, Southwest Petroleum University, Chengdu 610500, China
3 School of Petroleum and Natural Gas Engineering, Southwest Petroleum University, Chengdu 610500, China
4 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
Show less
文章历史+
Received
Published
Revised
2025-04-24
2026-04-08
2025-12-31
Online Date
2026-05-28
PDF (11149K)
摘要
玛湖区块致密砾岩储层破裂压力差异较大,易导致水平井分段压裂改造不均衡、生产效果较差,亟待准确预测压裂甜点提升水平井改造效果。为此,基于随机森林和交叉验证,筛选了致密砾岩储层破裂压力的主控因素,利用阿尔法进化算法(Alpha evolution,AE)优化双向长短时记忆网络的超参数,建立了破裂压力的组合预测模型,将破裂压力引入压裂甜点评价并计算压裂甜度,创新建立了致密砾岩储层的压裂甜点预测模型,并以玛湖区块现场数据为例进行了验证。结果表明,主控因素筛选和超参数优化有效提升了破裂压力组合预测模型的准确率,预测的均方根误差(root mean square error,RMSE)为0.75、平均绝对百分比误差(mean absolute percentage error,MAPE)为0.63%、决定系数R2为0.92;压裂甜度与产油剖面(flow scanning imaging,FSI)数据回归的R2为0.87;将压裂甜点预测模型迁移应用到不同区块R2仍超过0.70。研究认为,压裂甜度与产油量具有较强的相关性,建立的压裂甜点预测模型具有良好的适用性,能够有效指导致密砾岩储层水平井的压裂设计和分段分簇优化,为实现均衡改造和提高采收率提供技术支撑。
Abstract
The fracture pressure of tight conglomerate reservoirs in the Mahu Block varies significantly, which easily leads to unbalanced staged fracturing stimulation of horizontal wells and poor production performance. There is an urgent need to accurately predict fracturing sweet spots to improve the stimulation effect of horizontal wells. To this end, based on RF (random forest) and cross-validation, the primary controlling factors of fracture pressure in tight conglomerate reservoirs were screened. The hyperparameters of BiLSTM (bidirectional long short-term memory) network were optimized using AE (alpha evolution) algorithm, and a hybrid prediction model for fracture pressure was established. Fracture pressure was introduced into fracturing sweet spot evaluation to calculate fracturing sweetness, and an innovative fracturing sweet spot prediction model for tight conglomerate reservoirs was developed. Finally, the model was verified using field data from the Mahu Block. The results show that the screening of primary controlling factors and hyperparameter optimization have effectively improved the accuracy of the hybrid fracture pressure prediction model, with a prediction RMSE(root mean square error) of 0.75, MAPE (mean absolute percentage error) of 0.63%, and Root mean square error,R2 (coefficient of determination)of 0.92. The R2 of the regression between fracturing sweetness and FSI(flow scanning imaging) data is 0.87. When the fracturing sweet spot prediction model is applied to different blocks, the R2 still exceeds 0.70. The study concludes that fracturing sweetness has a strong correlation with oil production, and the established fracturing sweet spot prediction model has good applicability. It can effectively guide the fracturing design and staged-clustered optimization of horizontal wells in tight conglomerate reservoirs, providing technical support for achieving balanced reservoir modification and enhanced oil recovery.
CHENG Qi-di, HE Dai-lan, XU Hai-wei, KANG Yun-wei, DAI Ji-xiang, GUO Da-li, GUO Zi-xi.
Prediction and Optimization of Fracturing Sweet Spots for Horizontal Wells in Tight Conglomerate Reservoirs: Well MH01 in Mahu Block, Junggar Basin[J].
Science Technology and Engineering, 2026, 26(10): 4158-4166 DOI:10.12404/j.issn.1671-1815.2502975
ZhuWeiyao, YueMing, LiuYunfeng, et al. Research progress on development theory of tight oil reservoirs in China[J]. Journal of Engineering Science, 2019, 41(9): 1103-1114.
[3]
StephenR D. Prediction of fracture pressures for wildcat wells[J]. Journal of Petroleum Technology, 1982, 34(4): 863-872.
[4]
EatonB A. Fracture gradient prediction and its application in oilfield operations[J]. Journal of Petroleum Technology, 1969, 21(10): 1353-1360.
YangKun, LuoShangui, HuaLingxu, et al. Prediction of fracturing sweet spots in tight conglomerate reservoirs: a case study of Ma 18 well block[J]. Science Technology and Engineering, 2022, 22(32): 14174-14183.
LiMinxuan, SunJing, HuJiani, et al. Sweet spot optimization model for horizontal shale gas well sections[J]. Science Technology and Engineering, 2020, 20(24): 9844-9850.
ShenCheng, ZhaoJinzhou, RenLan, et al. A new method for identifying sweet spots of network fracturing in Longmaxi Formation shale gas reservoirs, Sichuan Basin[J]. Natural Gas Geoscience, 2019, 30(7): 937-945.
XuJiangwen, LiJianmin, WuYuanyue, et al. Exploration and practice of volume fracturing technology for horizontal wells in Mahu tight conglomerate reservoirs[J]. China Petroleum Exploration, 2019, 24(2): 241-249.
HuangAn, CaiWenyuan, WeiXinlu, et al. Lithology identification of volcanic rocks based on improved random forest algorithm[J]. Science Technology and Engineering, 2023, 23(9): 3696-3704.
ChenHong, YouYuzhu, JinHaibo, et al. Network intrusion detection method based on improved feature selection and CNN-BiLSTM[J]. Microelectronics & Computer, 2025. DOI: 10.19304/J.ISSN1000-7180.2024.0613.
[25]
GaoH, ZhangQ K. Alpha evolution: an efficient evolutionary algorithm with evolution path adaptation and matrix generation[J]. Engineering Applications of Artificial Intelligence, 2024, 137.DOI: 10.1016/j.engappai.2024.109202.
LiaoDongliang. Evaluation method and engineering application prospect of “dual sweet spots” in shale gas reservoirs[J]. Petro-leum Drilling Techniques, 2020, 48(4): 94-99.
[28]
FrankM, JamesI D. The paradox of increasing initial oil production but faster decline rates in fracking the Bakken Shale: implications for long term productivity of tight oil plays[J]. Journal of Petroleum Science and Engineering, 2022, 208(Part A). DOI: 10.1016/j.petrol.2021.109406.
WangXinzhu, ChenJiahao, RenZongxiao. Quantitative evaluation and optimization method of fracturing sweet spots in tight sandstone gas wells[J]. Natural Gas Exploration and Development, 2022, 45(4): 134-140.
LiKezhi. Identification method of fracturing “sweet spots” for horizontal wells in tight sandstone gas reservoirs of Daniudi Gas Field, Ordos Basin[J]. Petroleum Geology & Oilfield Development in Daqing, 2022, 41(6): 124-132.
ZhuJian, FanXibin, GaoYang, et al. Logging evaluation of original oil saturation in glutenite reservoirs of W Formation, MH Sag[J]. Fault-Block Oil & Gas Field, 2021, 28(4): 509-513.
ZhangFan, GaoMing, ChenGuojun, et al. Application of electrical imaging porosity spectrum in effective reservoir identification of glutenite[J]. Science Technology and Engineering, 2022, 22(2): 488-495.
GuoDali, WangYuji, ZhangXiaoshuan, et al. Fracture pressure prediction based on logging while drilling data[J]. Science Technology and Engineering, 2023, 23(5): 1923-1930.
ZongTingbo, ChenDezhao, YangDi, et al. Characteristics of tight sandstone reservoirs and factors controlling their physical properties of the Shanxi Formation in the western Hangjinqi of the Ordos Basin[J]. Natural Gas Geoscience, 2024, 35(4): 608-622.
ChenHaifeng, WangFengqi, WangMin. Characteristics and resource potential of the dense gravel gas reservoir of the Xujiayuanzi downfaulting shale group[J]. Journal of Central South University (Natural Science Edition), 2018, 49(1): 141-149.